Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2020-05-22

The following pull-request contains BPF updates for your *net* tree.

We've added 3 non-merge commits during the last 3 day(s) which contain
a total of 5 files changed, 69 insertions(+), 11 deletions(-).

The main changes are:

1) Fix to reject mmap()'ing read-only array maps as writable since BPF verifier
   relies on such map content to be frozen, from Andrii Nakryiko.

2) Fix breaking audit from secid_to_secctx() LSM hook by avoiding to use
   call_int_hook() since this hook is not stackable, from KP Singh.

3) Fix BPF flow dissector program ref leak on netns cleanup, from Jakub Sitnicki.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

kernel/bpf/syscall.c

@@ -623,9 +623,20 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	mutex_lock(&map->freeze_mutex);
 
-	if ((vma->vm_flags & VM_WRITE) && map->frozen) {
-		err = -EPERM;
-		goto out;
+	if (vma->vm_flags & VM_WRITE) {
+		if (map->frozen) {
+			err = -EPERM;
+			goto out;
+		}
+		/* map is meant to be read-only, so do not allow mapping as
+		 * writable, because it's possible to leak a writable page
+		 * reference and allows user-space to still modify it after
+		 * freezing, while verifier will assume contents do not change
+		 */
+		if (map->map_flags & BPF_F_RDONLY_PROG) {
+			err = -EACCES;
+			goto out;
+		}
 	}
 
 	/* set default open/close callbacks */

net/core/flow_dissector.c

@@ -160,12 +160,10 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 	return ret;
 }
 
-int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
+static int flow_dissector_bpf_prog_detach(struct net *net)
 {
 	struct bpf_prog *attached;
-	struct net *net;
 
-	net = current->nsproxy->net_ns;
 	mutex_lock(&flow_dissector_mutex);
 	attached = rcu_dereference_protected(net->flow_dissector_prog,
 					     lockdep_is_held(&flow_dissector_mutex));
@@ -179,6 +177,24 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
 	return 0;
 }
 
+int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
+{
+	return flow_dissector_bpf_prog_detach(current->nsproxy->net_ns);
+}
+
+static void __net_exit flow_dissector_pernet_pre_exit(struct net *net)
+{
+	/* We're not racing with attach/detach because there are no
+	 * references to netns left when pre_exit gets called.
+	 */
+	if (rcu_access_pointer(net->flow_dissector_prog))
+		flow_dissector_bpf_prog_detach(net);
+}
+
+static struct pernet_operations flow_dissector_pernet_ops __net_initdata = {
+	.pre_exit = flow_dissector_pernet_pre_exit,
+};
+
 /**
  * __skb_flow_get_ports - extract the upper layer ports and return them
  * @skb: sk_buff to extract the ports from
@@ -1836,7 +1852,7 @@ static int __init init_default_flow_dissectors(void)
 	skb_flow_dissector_init(&flow_keys_basic_dissector,
 				flow_keys_basic_dissector_keys,
 				ARRAY_SIZE(flow_keys_basic_dissector_keys));
-	return 0;
-}
 
+	return register_pernet_subsys(&flow_dissector_pernet_ops);
+}
 core_initcall(init_default_flow_dissectors);

security/security.c

@@ -1965,8 +1965,20 @@ EXPORT_SYMBOL(security_ismaclabel);
 
 int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
 {
-	return call_int_hook(secid_to_secctx, -EOPNOTSUPP, secid, secdata,
-				seclen);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Currently, only one LSM can implement secid_to_secctx (i.e this
+	 * LSM hook is not "stackable").
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.secid_to_secctx, list) {
+		rc = hp->hook.secid_to_secctx(secid, secdata, seclen);
+		if (rc != LSM_RET_DEFAULT(secid_to_secctx))
+			return rc;
+	}
+
+	return LSM_RET_DEFAULT(secid_to_secctx);
 }
 EXPORT_SYMBOL(security_secid_to_secctx);
 

tools/testing/selftests/bpf/prog_tests/mmap.c

@@ -19,7 +19,7 @@ void test_mmap(void)
 	const size_t map_sz = roundup_page(sizeof(struct map_data));
 	const int zero = 0, one = 1, two = 2, far = 1500;
 	const long page_size = sysconf(_SC_PAGE_SIZE);
-	int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd;
+	int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd, rdmap_fd;
 	struct bpf_map *data_map, *bss_map;
 	void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2;
 	struct test_mmap__bss *bss_data;
@@ -37,6 +37,17 @@ void test_mmap(void)
 	data_map = skel->maps.data_map;
 	data_map_fd = bpf_map__fd(data_map);
 
+	rdmap_fd = bpf_map__fd(skel->maps.rdonly_map);
+	tmp1 = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_SHARED, rdmap_fd, 0);
+	if (CHECK(tmp1 != MAP_FAILED, "rdonly_write_mmap", "unexpected success\n")) {
+		munmap(tmp1, 4096);
+		goto cleanup;
+	}
+	/* now double-check if it's mmap()'able at all */
+	tmp1 = mmap(NULL, 4096, PROT_READ, MAP_SHARED, rdmap_fd, 0);
+	if (CHECK(tmp1 == MAP_FAILED, "rdonly_read_mmap", "failed: %d\n", errno))
+		goto cleanup;
+
 	/* get map's ID */
 	memset(&map_info, 0, map_info_sz);
 	err = bpf_obj_get_info_by_fd(data_map_fd, &map_info, &map_info_sz);

tools/testing/selftests/bpf/progs/test_mmap.c

@@ -7,6 +7,14 @@
 
 char _license[] SEC("license") = "GPL";
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 4096);
+	__uint(map_flags, BPF_F_MMAPABLE | BPF_F_RDONLY_PROG);
+	__type(key, __u32);
+	__type(value, char);
+} rdonly_map SEC(".maps");
+
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 512 * 4); /* at least 4 pages of data */